Research on Fault Identification Algorithm for Photovoltaic Grid-Connected Inverter Based on VMD-Wavelet and SVM

Zian Wang

doi:10.47297/taposatWSP2633-456929.20260703

PDF
Export
Share
Collection
Album

Research on Fault Identification Algorithm for Photovoltaic Grid-Connected Inverter Based on VMD-Wavelet and SVM

Volume 7, Issue 3

Views: 0 Downloads: 5

Research on Fault Identification Algorithm for Photovoltaic Grid-Connected Inverter Based on VMD-Wavelet and SVM
Research on Fault Identification Algorithm for Photovoltaic Grid-Connected Inverter Based on VMD-Wavelet and SVM
Electrical Engineering and Automation, Shanghai Ocean University, Shanghai, 201306, China
Vol. 7, Issue 3, Pages: 142-147(2026)
Published：30 March 2026
DOI：10.47297/taposatWSP2633-456929.20260703
Accepted：

Scan QR Code

Wang Zian.Research on Fault Identification Algorithm for Photovoltaic Grid-Connected Inverter Based on VMD-Wavelet and SVM[J].Theory and Practice of Science and Technology,2026,07(03):142-147.
DOI：

Wang Zian.Research on Fault Identification Algorithm for Photovoltaic Grid-Connected Inverter Based on VMD-Wavelet and SVM[J].Theory and Practice of Science and Technology,2026,07(03):142-147. DOI： 10.47297/taposatWSP2633-456929.20260703.

摘要

Abstract

With the large-scale application of solar photovoltaic power generation technology

photovoltaic grid-connected inverters

as the core equipment for energy conversion between photovoltaic systems and public power grids

play a crucial role in ensuring the overall benefits of photovoltaic power generation systems. IGBT power switching devices operate under harsh conditions such as high voltage

high current

and high frequency for long periods

resulting in a high probability of open-circuit faults. Moreover

the circuit can still operate during the initial fault period

and external characteristics are not obvious. Traditional diagnostic methods have limited detection accuracy. This paper proposes a fault identification algorithm for photovoltaic grid-connected inverters based on Variational Mode Decomposition (VMD)

Wavelet Packet Transform

and Support Vector Machine (SVM). The algorithm uses three-phase output current from the AC side as the fault observation signal

adaptively decomposes the signal into several band-limited modal components using VMD

and determines the optimal modal number using the minimum sample entropy criterion. Three-layer wavelet packet transform is applied to each modal component

and wavelet packet energy of each sub-band is calculated to form a high-dimensional fault feature vector. After normalization

the feature vector is input into a multi-class SVM classifier to complete accurate fault type identification. A simulation model of three-phase two-level photovoltaic grid-connected inverter is built on MATLAB/Simulink platform. 280 sets of sample data are generated for 7 types of working conditions including 6 IGBT single-device open-circuit faults and normal operation. Experimental results show that the proposed method achieves identification accuracy above 98.5% for all fault types

and maintains good robustness and anti-interference ability under low signal-to-noise ratio conditions.

关键词

Keywords

references

Wang J, Shao H, Peng Y, et al. PSparseFormer: Enhancing Fault Feature Extraction Based on Parallel Sparse Self-Attention and Multiscale Broadcast Feedforward Block[J]. IEEE Internet of Things Journal, 2024, 11(13): 22982-22991.

Wang Y, Cao G. A multiscale convolution neural network for bearing fault diagnosis based on frequency division denoising under complex noise conditions[J]. Complex & Intelligent Systems, 2022, 9(4): 4263-4285.

Li S, Jin N, Dogani A, et al. Enhancing LightGBM for Industrial Fault Warning: An Innovative Hybrid Algorithm[J]. Processes, 2024, 12(1): 221.

Suliman F, Anayi F, Packianather M. Electrical Faults Analysis and Detection in Photovoltaic Arrays Based on Machine Learning Classifiers[J]. Sustainability, 2024, 16(3): 1102.

Liu L, Shi N, Maharjan S, et al. Siamese Convolutional Neural Network-Based Anomaly Detection for Distributed PV Inverter[C]. IEEE Power & Energy Society General Meeting, 2021.

Yang Y, Haque M, Bai D, et al. Fault Diagnosis of Electric Motors Using Deep Learning Algorithms and Its Application: A Review[J]. Energies, 2021, 14(21): 7017.

Jiang Y Y, Cheng H, Cui J, et al. Soft Fault Diagnosis of Photovoltaic Inverter Based on VMD Wavelet Energy[J]. Proceedings of the CSU-EPSA, 2018, 30(11): 19-25.

Zhang B D, Yu H N, Luo R Q, et al. Research on Parameter Fault Diagnosis of Photovoltaic Grid-Connected In VMD-WPEverters Based on and MPA-LSTM[J]. Proceedings of the CSU-EPSA, 2023, 35(2): 140-147.

Zhou C Y, Shen Y X. Open-Circuit Fault Diagnosis of Dual Three-Phase Voltage Source Inverter Based on Wavelet Analysis[J]. Electric Machines and Control, 2020, 24(9): 65-75.

Jiang Y Y, Zhang S T. Research on Soft Fault Diagnosis Method of Photovoltaic Inverter Based on Improved VMD and CNN Neural Network[J]. Electrical Measurement & Instrumentation, 2021, 58(2): 158-163.

Ma M Y, Ling F, Sun Y R, et al. Review of Intelligent Fault Diagnosis Methods for Three-Phase Voltage Source Inverters[J]. Proceedings of the CSEE, 2020, 40(23): 7683-7698.

Geng Y W, Li W, Wang K. A Fault Diagnosis Method for Three-Phase Photovoltaic Grid-Connected Inverters[J]. Transactions of China Electrotechnical Society, 2014, 29(S1): 203-209.

Sun Q, Peng F, Li H S, et al. Fault Diagnosis of Inverters Based on CGAN-CNN Under Sample Imbalance[J]. Journal of Power Supply, 2023.

Wang H L, Wang X G, Li J J, et al. Bridge Arm Fault Diagnosis of MMC-MG System Based on Improved Support Vector Machine[J]. Power System Protection and Control, 2023, 51(7): 1-13.

Xia Y Y, Zhang Z, Li X C, et al. Small Current Grounding Fault Selection Method Based on FastICA[J]. Electrical & Energy Management Technology, 2018(17): 63-68.